Llama 4 Maverick
Llama 4 Community LicenseDeveloped by Meta · Multimodal Sparse MoE (17B Active / 400B Total) · Modalities: Text, Vision · Released 2025-04-05
What are the token costs and operational benchmarks for Llama 4 Maverick?
Verified Capability Benchmarks
Composite Intelligence: 75.9/100Architectural & Production Profile
Meta's flagship 128-expert open-weight multimodal MoE model delivering 1M context and rapid LPU/CS-3 inference throughput.
High-throughput open-weight multimodal assistants, enterprise RAG, and low-cost cloud inference on Groq and Cerebras.
- Architecture
- Multimodal Sparse MoE (17B Active / 400B Total)
- Modalities
- Text, Vision
- Max Output Tokens
- 32,768 tokens
- Blended Rate (3:1)
- $0.300 / 1M
Verified Cloud Inference Endpoints Hosting Llama 4 Maverick
Compare latency, streaming speed, and token pricing across cloud API providers.
| Inference Provider | Role | Input / 1M | Output / 1M | Avg TTFT | Throughput |
|---|---|---|---|---|---|
| Google Gemini & Vertex AI → | Partner Endpoint | $0.20 | $0.60 | 150ms | 183.8 tok/s |
| Groq LPU Inference → | Primary Host | $0.20 | $0.60 | 80ms | 420 tok/s |
| Cerebras CS-3 Wafer-Scale Inference → | Partner Endpoint | $0.20 | $0.60 | 70ms | 560 tok/s |
Interactive Monthly Token Economics & ROI Forecaster
Model production workloads across prompt, completion, and cached context tokens, or switch models on the fly.
Estimated Monthly Spend
$0.20/1M in · $0.60/1M out
Prompt Cache: $0.050/1M read · $0.20/1M write
$2.00/1M in · $10.00/1M out
Prompt Cache: $0.100/1M read · $0.50/1M write
Head-to-Head Comparisons Involving Llama 4 Maverick (36)
Llama 4 Maverick vs Gemini 4 Argon
Llama 4 Maverick is 90.0% cheaper for input tokens ($0.20 vs. $2.00 per 1M tokens) and $0.60 vs. $10.00 for output tokens (10.0x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (715ms faster than Gemini 4 Argon) with 175 vs. 115 tok/s throughput. Gemini 4 Argon leads coding evaluations at 84.5% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 93.8% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs Claude 4.5 Sonnet
Llama 4 Maverick is 93.3% cheaper for input tokens ($0.20 vs. $3.00 per 1M tokens) and $0.60 vs. $15.00 for output tokens (15.0x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (245ms faster than Claude 4.5 Sonnet) with 175 vs. 84 tok/s throughput. Claude 4.5 Sonnet leads coding evaluations at 75.8% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 84.2% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs Claude Opus 5.5
Llama 4 Maverick is 95.0% cheaper for input tokens ($0.20 vs. $4.00 per 1M tokens) and $0.60 vs. $20.00 for output tokens (20.0x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (545ms faster than Claude Opus 5.5) with 175 vs. 95 tok/s throughput. Claude Opus 5.5 leads coding evaluations at 89.9% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 93.2% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs Gemini 3.8 Flash
Llama 4 Maverick is 20.0% cheaper for input tokens ($0.20 vs. $0.25 per 1M tokens) and $0.60 vs. $1.50 for output tokens (1.2x cost advantage). In terms of operational performance, Gemini 3.8 Flash delivers lower response latency at 105ms TTFT (30ms faster than Llama 4 Maverick) with 210 vs. 175 tok/s throughput. Gemini 3.8 Flash leads coding evaluations at 68.5% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 79.2% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs GPT-5
Llama 4 Maverick is 92.0% cheaper for input tokens ($0.20 vs. $2.50 per 1M tokens) and $0.60 vs. $10.00 for output tokens (12.5x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (205ms faster than GPT-5) with 175 vs. 105 tok/s throughput. GPT-5 leads coding evaluations at 74.9% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 85.4% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs GPT-6 Astra
Llama 4 Maverick is 98.0% cheaper for input tokens ($0.20 vs. $10.00 per 1M tokens) and $0.60 vs. $50.00 for output tokens (50.0x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (605ms faster than GPT-6 Astra) with 175 vs. 74 tok/s throughput. GPT-6 Astra leads coding evaluations at 75.7% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 96.0% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs DeepSeek V4 Pro
Llama 4 Maverick is 84.8% cheaper for input tokens ($0.20 vs. $1.32 per 1M tokens) and $0.60 vs. $3.96 for output tokens (6.6x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (385ms faster than DeepSeek V4 Pro) with 175 vs. 78 tok/s throughput. DeepSeek V4 Pro leads coding evaluations at 80.6% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 90.1% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs DeepSeek R1
Llama 4 Maverick is 63.6% cheaper for input tokens ($0.20 vs. $0.55 per 1M tokens) and $0.60 vs. $2.19 for output tokens (2.8x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (1315ms faster than DeepSeek R1) with 175 vs. 58 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 49.2% for DeepSeek R1 and 73.8% vs. 71.5% on GPQA Diamond.
Llama 4 Maverick vs DeepSeek V4 Flash Vision (Exp)
Llama 4 Maverick is 9.1% cheaper for input tokens ($0.20 vs. $0.22 per 1M tokens) and $0.60 vs. $0.65 for output tokens (1.1x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (175ms faster than DeepSeek V4 Flash Vision (Exp)) with 175 vs. 165 tok/s throughput. DeepSeek V4 Flash Vision (Exp) leads coding evaluations at 77.4% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 91.3% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs OpenAI o3
Llama 4 Maverick is 90.0% cheaper for input tokens ($0.20 vs. $2.00 per 1M tokens) and $0.60 vs. $8.00 for output tokens (10.0x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (1015ms faster than OpenAI o3) with 175 vs. 82 tok/s throughput. OpenAI o3 leads coding evaluations at 71.7% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 87.7% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs Claude 4 Opus
Llama 4 Maverick is 98.7% cheaper for input tokens ($0.20 vs. $15.00 per 1M tokens) and $0.60 vs. $75.00 for output tokens (75.0x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (785ms faster than Claude 4 Opus) with 175 vs. 46 tok/s throughput. Claude 4 Opus leads coding evaluations at 77.2% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 87.1% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs Claude 3.7 Sonnet
Llama 4 Maverick is 93.3% cheaper for input tokens ($0.20 vs. $3.00 per 1M tokens) and $0.60 vs. $15.00 for output tokens (15.0x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (405ms faster than Claude 3.7 Sonnet) with 175 vs. 72 tok/s throughput. Claude 3.7 Sonnet leads coding evaluations at 70.3% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 78.5% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs Gemini 3.1 Pro
Llama 4 Maverick is 84.0% cheaper for input tokens ($0.20 vs. $1.25 per 1M tokens) and $0.60 vs. $10.00 for output tokens (6.2x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (285ms faster than Gemini 3.1 Pro) with 175 vs. 98 tok/s throughput. Gemini 3.1 Pro leads coding evaluations at 71.8% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 82.4% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs Grok 4
Llama 4 Maverick is 92.0% cheaper for input tokens ($0.20 vs. $2.50 per 1M tokens) and $0.60 vs. $12.50 for output tokens (12.5x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (345ms faster than Grok 4) with 175 vs. 95 tok/s throughput. Grok 4 leads coding evaluations at 73.2% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 86.2% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs Qwen 3.8 Flash Next
Qwen 3.8 Flash Next is 20.0% cheaper for input tokens ($0.16 vs. $0.20 per 1M tokens) and $0.47 vs. $0.60 for output tokens (1.2x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (145ms faster than Qwen 3.8 Flash Next) with 175 vs. 185 tok/s throughput. Qwen 3.8 Flash Next leads coding evaluations at 81.0% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 91.7% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs Gemini 3.5 Flash-Lite
Gemini 3.5 Flash-Lite is 62.5% cheaper for input tokens ($0.07 vs. $0.20 per 1M tokens) and $0.30 vs. $0.60 for output tokens (2.7x cost advantage). In terms of operational performance, Gemini 3.5 Flash-Lite delivers lower response latency at 78ms TTFT (57ms faster than Llama 4 Maverick) with 265 vs. 175 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 55.4% for Gemini 3.5 Flash-Lite and 73.8% vs. 68.4% on GPQA Diamond.
Llama 4 Maverick vs OpenAI o4-mini
Llama 4 Maverick is 81.8% cheaper for input tokens ($0.20 vs. $1.10 per 1M tokens) and $0.60 vs. $4.40 for output tokens (5.5x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (545ms faster than OpenAI o4-mini) with 175 vs. 125 tok/s throughput. OpenAI o4-mini leads coding evaluations at 68.1% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 81.4% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs DeepSeek V3
DeepSeek V3 is 30.0% cheaper for input tokens ($0.14 vs. $0.20 per 1M tokens) and $0.28 vs. $0.60 for output tokens (1.4x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (275ms faster than DeepSeek V3) with 175 vs. 78 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 42.0% for DeepSeek V3 and 73.8% vs. 59.1% on GPQA Diamond.
Llama 4 Maverick vs Gemma 4 31B IT
Gemma 4 31B IT is 40.0% cheaper for input tokens ($0.12 vs. $0.20 per 1M tokens) and $0.36 vs. $0.60 for output tokens (1.7x cost advantage). In terms of operational performance, Gemma 4 31B IT delivers lower response latency at 115ms TTFT (20ms faster than Llama 4 Maverick) with 155 vs. 175 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 59.2% for Gemma 4 31B IT and 73.8% vs. 71.2% on GPQA Diamond.
Llama 4 Maverick vs OpenAI o3-mini
Llama 4 Maverick is 81.8% cheaper for input tokens ($0.20 vs. $1.10 per 1M tokens) and $0.60 vs. $4.40 for output tokens (5.5x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (815ms faster than OpenAI o3-mini) with 175 vs. 98 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 49.3% for OpenAI o3-mini and 73.8% vs. 79.7% on GPQA Diamond.
Llama 4 Maverick vs Claude 3.5 Haiku
Llama 4 Maverick is 75.0% cheaper for input tokens ($0.20 vs. $0.80 per 1M tokens) and $0.60 vs. $4.00 for output tokens (4.0x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (55ms faster than Claude 3.5 Haiku) with 175 vs. 130 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 40.6% for Claude 3.5 Haiku and 73.8% vs. 41.6% on GPQA Diamond.
Llama 4 Maverick vs Claude 3.5 Sonnet
Llama 4 Maverick is 93.3% cheaper for input tokens ($0.20 vs. $3.00 per 1M tokens) and $0.60 vs. $15.00 for output tokens (15.0x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (175ms faster than Claude 3.5 Sonnet) with 175 vs. 80 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 49.0% for Claude 3.5 Sonnet and 73.8% vs. 59.4% on GPQA Diamond.
Llama 4 Maverick vs Gemini 2.0 Flash
Gemini 2.0 Flash is 50.0% cheaper for input tokens ($0.10 vs. $0.20 per 1M tokens) and $0.40 vs. $0.60 for output tokens (2.0x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (145ms faster than Gemini 2.0 Flash) with 175 vs. 185 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 51.8% for Gemini 2.0 Flash and 73.8% vs. 63.6% on GPQA Diamond.
Llama 4 Maverick vs Gemini 2.5 Flash
Llama 4 Maverick is 33.3% cheaper for input tokens ($0.20 vs. $0.30 per 1M tokens) and $0.60 vs. $2.50 for output tokens (1.5x cost advantage). In terms of operational performance, Gemini 2.5 Flash delivers lower response latency at 110ms TTFT (25ms faster than Llama 4 Maverick) with 180 vs. 175 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 58.0% for Gemini 2.5 Flash and 73.8% vs. 70.5% on GPQA Diamond.
Llama 4 Maverick vs Gemini 2.5 Pro
Llama 4 Maverick is 84.0% cheaper for input tokens ($0.20 vs. $1.25 per 1M tokens) and $0.60 vs. $10.00 for output tokens (6.2x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (565ms faster than Gemini 2.5 Pro) with 175 vs. 80 tok/s throughput. Gemini 2.5 Pro leads coding evaluations at 63.8% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 74.0% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs GLM-5.3-Flash
GLM-5.3-Flash is 40.0% cheaper for input tokens ($0.12 vs. $0.20 per 1M tokens) and $0.40 vs. $0.60 for output tokens (1.7x cost advantage). In terms of operational performance, GLM-5.3-Flash delivers lower response latency at 90ms TTFT (45ms faster than Llama 4 Maverick) with 175 vs. 175 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 52.8% for GLM-5.3-Flash and 73.8% vs. 63.5% on GPQA Diamond.
Llama 4 Maverick vs GLM-5.3
Llama 4 Maverick is 42.9% cheaper for input tokens ($0.20 vs. $0.35 per 1M tokens) and $0.60 vs. $1.00 for output tokens (1.7x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (25ms faster than GLM-5.3) with 175 vs. 120 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 56.0% for GLM-5.3 and 73.8% vs. 67.0% on GPQA Diamond.
Llama 4 Maverick vs GPT-4o Mini
GPT-4o Mini is 25.0% cheaper for input tokens ($0.15 vs. $0.20 per 1M tokens) and $0.60 vs. $0.60 for output tokens (1.3x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (85ms faster than GPT-4o Mini) with 175 vs. 140 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 41.0% for GPT-4o Mini and 73.8% vs. 40.2% on GPQA Diamond.
Llama 4 Maverick vs GPT-4o
Llama 4 Maverick is 92.0% cheaper for input tokens ($0.20 vs. $2.50 per 1M tokens) and $0.60 vs. $10.00 for output tokens (12.5x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (145ms faster than GPT-4o) with 175 vs. 100 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 48.0% for GPT-4o and 73.8% vs. 53.6% on GPQA Diamond.
Llama 4 Maverick vs GPT-6.1 Sol
Llama 4 Maverick is 90.0% cheaper for input tokens ($0.20 vs. $2.00 per 1M tokens) and $0.60 vs. $10.00 for output tokens (10.0x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (385ms faster than GPT-6.1 Sol) with 175 vs. 135 tok/s throughput. GPT-6.1 Sol leads coding evaluations at 86.4% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 92.4% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs Grok 3 Mini
Llama 4 Maverick is 33.3% cheaper for input tokens ($0.20 vs. $0.30 per 1M tokens) and $0.60 vs. $1.20 for output tokens (1.5x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (15ms faster than Grok 3 Mini) with 175 vs. 160 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 54.0% for Grok 3 Mini and 73.8% vs. 68.0% on GPQA Diamond.
Llama 4 Maverick vs Grok 3
Llama 4 Maverick is 93.3% cheaper for input tokens ($0.20 vs. $3.00 per 1M tokens) and $0.60 vs. $15.00 for output tokens (15.0x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (485ms faster than Grok 3) with 175 vs. 88 tok/s throughput. Grok 3 leads coding evaluations at 65.8% SWE-bench Verified vs. 62.4% for Llama 4 Maverick and 84.6% vs. 73.8% on GPQA Diamond.
Llama 4 Maverick vs Llama 3.3 70B Instruct
Llama 3.3 70B Instruct is 40.0% cheaper for input tokens ($0.12 vs. $0.20 per 1M tokens) and $0.30 vs. $0.60 for output tokens (1.7x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (10ms faster than Llama 3.3 70B Instruct) with 175 vs. 165 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 42.5% for Llama 3.3 70B Instruct and 73.8% vs. 55.6% on GPQA Diamond.
Llama 4 Maverick vs Mistral Large 2 (2411)
Llama 4 Maverick is 90.0% cheaper for input tokens ($0.20 vs. $2.00 per 1M tokens) and $0.60 vs. $6.00 for output tokens (10.0x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (245ms faster than Mistral Large 2 (2411)) with 175 vs. 75 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 45.2% for Mistral Large 2 (2411) and 73.8% vs. 54.2% on GPQA Diamond.
Llama 4 Maverick vs o1
Llama 4 Maverick is 98.7% cheaper for input tokens ($0.20 vs. $15.00 per 1M tokens) and $0.60 vs. $60.00 for output tokens (75.0x cost advantage). In terms of operational performance, Llama 4 Maverick delivers lower response latency at 135ms TTFT (2465ms faster than o1) with 175 vs. 48 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 48.9% for o1 and 73.8% vs. 78.0% on GPQA Diamond.
Llama 4 Maverick vs Qwen 3.8 27B
Llama 4 Maverick and Qwen 3.8 27B share identical input pricing at $0.20 per 1M tokens ($0.60 vs. $0.60 output). In terms of operational performance, Qwen 3.8 27B delivers lower response latency at 120ms TTFT (15ms faster than Llama 4 Maverick) with 140 vs. 175 tok/s throughput. Llama 4 Maverick leads coding evaluations at 62.4% SWE-bench Verified vs. 58.4% for Qwen 3.8 27B and 73.8% vs. 68.0% on GPQA Diamond.
Frequently Asked Questions & Query Fan-Out
How much does Llama 4 Maverick cost per 1M tokens including prompt caching?
Llama 4 Maverick costs $0.20 per million input tokens and $0.60 per million output tokens. Cached input reads cost $0.050 per 1M tokens, reducing repeated context costs by 75%.
What are Llama 4 Maverick's coding and reasoning benchmark scores?
Llama 4 Maverick achieves 62.4% on SWE-bench Verified, 92.6% on HumanEval coding, 73.8% on GPQA Diamond graduate-level science, 84.5% on MMLU-Pro, and 91% on MATH-500, earning an overall Inference Value Ratio (IVR) of 77/100.
What is the context window, TTFT latency, and token throughput of Llama 4 Maverick?
Llama 4 Maverick supports a 1,048,576 token context window (32,768 max output tokens) and operates at 135ms average Time to First Token (TTFT) with 175 tokens/sec output streaming throughput.
What are the primary production use cases for Llama 4 Maverick?
High-throughput open-weight multimodal assistants, enterprise RAG, and low-cost cloud inference on Groq and Cerebras.